reconciling

README.md

@@ -1,2 +1,8 @@
 # Talks
 Repository for development of talks
+
+|Directory | Contents |
+|---|---| 
+|ctnt2018 | ECM Method @ Connecticut Number Theory Week, June, 2018 |
+|jax_gl | Random Walk methods @ JAX working group on graph embedding, July 2018|
+

jax_gl/Untitled.ipynb

@@ -0,0 +1,83 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.neural_network import MLPClassifier"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X=np.array([1,0,0,1])\n",
+    "X.shape=(2,2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[1, 0],\n",
+       "       [0, 1]])"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "clf=MLPClassifier(solver='lbfgs',alpha=.0001,hidden_layer_sizes=())"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

jax_gl/graph.tex

@@ -0,0 +1,29 @@
+\documentclass{beamer}
+\begin{document}
+\begin{frame}
+\begin{center}
+Overview of \\
+Section 4.2.1: DL based Graph Embedding with Random Walk \\
+from \\
+\textit{A comprehensive survey of graph embedding: problems, techniques, and applications} \\
+\textit{Cai, et. al.} \\
+\textit{IEEE Transactions on Knowledge and Data Engineering, Sept. 2017} \\
+\end{center}
+
+Jeremy Teitelbaum \\
+July, 2018
+
+\end{frame}
+\begin{frame}{Context}
+\begin{problem}
+Given a finite graph $G$, find an embedding of $G$ into a relatively low dimensional Euclidean space in a way that captures
+relevant information about the structure of the graph.
+\end{problem}
+\bigskip\noindent
+\textbf{Deep Learning} algorithms in general are typically based on neural networks and are characterized by non-linearity and hierarchical structure.  
+
+\bigskip\noindent
+Deep learning techniques for graph embedding sample structure from a large graph and apply techniques arising from
+natural language processing to those samples to construct an embedding.
+\end{frame}
+\end{document}

jax_gl/graph.tex~

@@ -0,0 +1,11 @@
+\documentclass{beamer}
+\begin{document}
+\begin{frame}
+\begin{center}
+DL based Graph Embedding with Random Walk \\
+from \\
+\texit{A comprehensive survey of graph embedding: problems, techniques, and applications} \\
+\textit{by Cai, et. al.}
+\textit{IEEE Transactions on Knowledge and Data Engineering, Sept. 2017}
+\end{frame}
+\end{document}